用例库
浏览所有评测维度和用例,查看各模型的生成结果对比
L-AgentMCP
L-ChinesePinyin
L-Code
L-Comprehension
L-Consistency
L-Context
L-Creative
L-Instruction
L-Knowledge
L-Logic
L-Math
L-Multilingual
L-QA
L-ReasoningChain
L-Roleplay
L-Safety
L-Summary
L-Translation
L-Writing
L-Hallucination
L-CriticalThinking
L-Polish
L-Context
xsct-l
引用追踪
L-Context
xsct-l
矛盾检测
L-Context
xsct-l
长文本一致性
L-Context
xsct-l
文档问答
L-Context
xsct-l
跨段落推理
L-Context
xsct-l
多轮对话记忆
L-Context
xsct-l
信息提取
L-Context
xsct-l
对话追踪
L-Context
xsct-l